IronOCR 和 Nanonets OCR 之间的比较

// AWS Textract: 多页PDF requires S3 + async job
public async Task<string> ProcessPdfAsync(string pdfPath)
{
    // Step 1: Upload to S3 — credentials for two services required
    var key = $"uploads/{Guid.NewGuid()}.pdf";
    using (var fileStream = File.OpenRead(pdfPath))
    {
        await _s3Client.PutObjectAsync(new PutObjectRequest
        {
            BucketName = _bucketName,
            Key = key,
            InputStream = fileStream
        });
    }

    try
    {
        // Step 2: Start async Textract job
        var startResponse = await _textractClient.StartDocumentTextDetectionAsync(
            new StartDocumentTextDetectionRequest
            {
                DocumentLocation = new DocumentLocation
                {
                    S3Object = new S3Object { Bucket = _bucketName, Name = key }
                }
            });

        var jobId = startResponse.JobId;

        // Step 3: Poll every 5 seconds until complete
        GetDocumentTextDetectionResponse getResponse;
        do
        {
            await Task.Delay(5000);
            getResponse = await _textractClient.GetDocumentTextDetectionAsync(
                new GetDocumentTextDetectionRequest { JobId = jobId });
        } while (getResponse.JobStatus == JobStatus.IN_PROGRESS);

        if (getResponse.JobStatus != JobStatus.SUCCEEDED)
            throw new Exception($"Textract job failed: {getResponse.StatusMessage}");

        // Step 4: Paginate through result blocks
        var allText = new StringBuilder();
        string nextToken = null;
        do
        {
            var pageResponse = await _textractClient.GetDocumentTextDetectionAsync(
                new GetDocumentTextDetectionRequest
                {
                    JobId = jobId,
                    NextToken = nextToken
                });

            foreach (var block in pageResponse.Blocks.Where(b => b.BlockType == BlockType.LINE))
                allText.AppendLine(block.Text);

            nextToken = pageResponse.NextToken;
        } while (nextToken != null);

        return allText.ToString();
    }
    finally
    {
        // Step 5: 总是 clean up S3
        await _s3Client.DeleteObjectAsync(_bucketName, key);
    }
}

Imports System
Imports System.IO
Imports System.Text
Imports System.Threading.Tasks
Imports Amazon.S3
Imports Amazon.Textract
Imports Amazon.Textract.Model

Public Class PdfProcessor
    Private _s3Client As IAmazonS3
    Private _textractClient As IAmazonTextract
    Private _bucketName As String

    Public Async Function ProcessPdfAsync(pdfPath As String) As Task(Of String)
        ' Step 1: Upload to S3 — credentials for two services required
        Dim key = $"uploads/{Guid.NewGuid()}.pdf"
        Using fileStream = File.OpenRead(pdfPath)
            Await _s3Client.PutObjectAsync(New PutObjectRequest With {
                .BucketName = _bucketName,
                .Key = key,
                .InputStream = fileStream
            })
        End Using

        Try
            ' Step 2: Start async Textract job
            Dim startResponse = Await _textractClient.StartDocumentTextDetectionAsync(
                New StartDocumentTextDetectionRequest With {
                    .DocumentLocation = New DocumentLocation With {
                        .S3Object = New S3Object With {.Bucket = _bucketName, .Name = key}
                    }
                })

            Dim jobId = startResponse.JobId

            ' Step 3: Poll every 5 seconds until complete
            Dim getResponse As GetDocumentTextDetectionResponse
            Do
                Await Task.Delay(5000)
                getResponse = Await _textractClient.GetDocumentTextDetectionAsync(
                    New GetDocumentTextDetectionRequest With {.JobId = jobId})
            Loop While getResponse.JobStatus = JobStatus.IN_PROGRESS

            If getResponse.JobStatus <> JobStatus.SUCCEEDED Then
                Throw New Exception($"Textract job failed: {getResponse.StatusMessage}")
            End If

            ' Step 4: Paginate through result blocks
            Dim allText = New StringBuilder()
            Dim nextToken As String = Nothing
            Do
                Dim pageResponse = Await _textractClient.GetDocumentTextDetectionAsync(
                    New GetDocumentTextDetectionRequest With {
                        .JobId = jobId,
                        .NextToken = nextToken
                    })

                For Each block In pageResponse.Blocks.Where(Function(b) b.BlockType = BlockType.LINE)
                    allText.AppendLine(block.Text)
                Next

                nextToken = pageResponse.NextToken
            Loop While nextToken IsNot Nothing

            Return allText.ToString()
        Finally
            ' Step 5: 总是 clean up S3
            Await _s3Client.DeleteObjectAsync(_bucketName, key)
        End Try
    End Function
End Class

// Every call to this method costs money — per page, permanently
public async Task<string> DetectTextAsync(string imagePath)
{
    var imageBytes = File.ReadAllBytes(imagePath);  // Image leaves your network

    var request = new DetectDocumentTextRequest
    {
        Document = new Document
        {
            Bytes = new MemoryStream(imageBytes)
        }
    };

    var response = await _client.DetectDocumentTextAsync(request);  // per-page charge

    return string.Join("\n", response.Blocks
        .Where(b => b.BlockType == BlockType.LINE)
        .Select(b => b.Text));
}

Imports System.IO
Imports System.Threading.Tasks

' Every call to this method costs money — per page, permanently
Public Async Function DetectTextAsync(imagePath As String) As Task(Of String)
    Dim imageBytes = File.ReadAllBytes(imagePath)  ' Image leaves your network

    Dim request = New DetectDocumentTextRequest With {
        .Document = New Document With {
            .Bytes = New MemoryStream(imageBytes)
        }
    }

    Dim response = Await _client.DetectDocumentTextAsync(request)  ' per-page charge

    Return String.Join(vbLf, response.Blocks _
        .Where(Function(b) b.BlockType = BlockType.LINE) _
        .Select(Function(b) b.Text))
End Function

// One license. 否 per-page cost. Same code handles 1 page or 1,000,000.
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

var text = new IronTesseract().Read("document.jpg").Text;

Imports IronOcr

' One license. 否 per-page cost. Same code handles 1 page or 1,000,000.
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

Dim text As String = New IronTesseract().Read("document.jpg").Text

// This code sends PHI, legal documents, financial records — whatever is in
// the file — to Amazon Web Services infrastructure
public async Task<string> ProcessSensitiveDocumentAsync(string documentPath)
{
    var imageBytes = File.ReadAllBytes(documentPath);

    // Data crosses your security perimeter here
    var request = new DetectDocumentTextRequest
    {
        Document = new Document
        {
            Bytes = new MemoryStream(imageBytes)
        }
    };

    // Amazon processes it; you receive text back
    var response = await _client.DetectDocumentTextAsync(request);

    return string.Join("\n", response.Blocks
        .Where(b => b.BlockType == BlockType.LINE)
        .Select(b => b.Text));
}

Imports System.IO
Imports System.Threading.Tasks
Imports Amazon.Textract
Imports Amazon.Textract.Model

Public Class DocumentProcessor
    Private _client As AmazonTextractClient

    Public Sub New(client As AmazonTextractClient)
        _client = client
    End Sub

    ' This code sends PHI, legal documents, financial records — whatever is in
    ' the file — to Amazon Web Services infrastructure
    Public Async Function ProcessSensitiveDocumentAsync(documentPath As String) As Task(Of String)
        Dim imageBytes = File.ReadAllBytes(documentPath)

        ' Data crosses your security perimeter here
        Dim request As New DetectDocumentTextRequest With {
            .Document = New Document With {
                .Bytes = New MemoryStream(imageBytes)
            }
        }

        ' Amazon processes it; you receive text back
        Dim response = Await _client.DetectDocumentTextAsync(request)

        Return String.Join(vbLf, response.Blocks _
            .Where(Function(b) b.BlockType = BlockType.LINE) _
            .Select(Function(b) b.Text))
    End Function
End Class

// IronOCR: document bytes never leave this process
public string ProcessSensitiveDocument(string documentPath)
{
    // Processes entirely on local hardware — no network call
    var ocr = new IronTesseract();
    return ocr.Read(documentPath).Text;
}

' IronOCR: document bytes never leave this process
Public Function ProcessSensitiveDocument(documentPath As String) As String
    ' Processes entirely on local hardware — no network call
    Dim ocr As New IronTesseract()
    Return ocr.Read(documentPath).Text
End Function

// Full production-grade async processor for Textract PDF handling
public class TextractAsyncProcessor
{
    private readonly AmazonTextractClient _textractClient;
    private readonly AmazonS3Client _s3Client;
    private readonly string _bucketName;
    private readonly TimeSpan _pollInterval = TimeSpan.FromSeconds(5);
    private readonly TimeSpan _maxWaitTime = TimeSpan.FromMinutes(10);

    public async Task<DocumentResult> ProcessDocumentAsync(
        string localFilePath,
        CancellationToken cancellationToken = default)
    {
        var s3Key = $"textract-uploads/{Guid.NewGuid()}{Path.GetExtension(localFilePath)}";

        try
        {
            // Phase 1: Upload to S3
            await UploadToS3Async(localFilePath, s3Key, cancellationToken);

            // Phase 2: Start Textract job
            var jobId = await StartTextractJobAsync(s3Key, cancellationToken);

            // Phase 3: Poll until complete (up to 10 minutes)
            var pollResult = await PollForCompletionAsync(jobId, cancellationToken);

            if (!pollResult.Success)
                throw new Exception($"Textract job failed: {pollResult.ErrorMessage}");

            // Phase 4: Retrieve paginated results
            return await GetAllResultsAsync(jobId, cancellationToken);
        }
        finally
        {
            // Phase 5: S3 cleanup — must succeed or storage costs accumulate
            await DeleteFromS3Async(s3Key, cancellationToken);
        }
    }

    private async Task<(bool Success, string ErrorMessage)> PollForCompletionAsync(
        string jobId, CancellationToken cancellationToken)
    {
        var startTime = DateTime.UtcNow;
        int pollCount = 0;

        while (DateTime.UtcNow - startTime < _maxWaitTime)
        {
            cancellationToken.ThrowIfCancellationRequested();

            var response = await _textractClient.GetDocumentTextDetectionAsync(
                new GetDocumentTextDetectionRequest { JobId = jobId }, cancellationToken);

            pollCount++;

            switch (response.JobStatus)
            {
                case JobStatus.SUCCEEDED: return (true, null);
                case JobStatus.FAILED: return (false, response.StatusMessage ?? "Unknown error");
                case JobStatus.IN_PROGRESS:
                    await Task.Delay(_pollInterval, cancellationToken);
                    break;
                default:
                    throw new Exception($"Unknown job status: {response.JobStatus}");
            }
        }

        return (false, "Job timed out");
    }
}

Imports System
Imports System.IO
Imports System.Threading
Imports System.Threading.Tasks
Imports Amazon.Textract
Imports Amazon.S3
Imports Amazon.Textract.Model

' Full production-grade async processor for Textract PDF handling
Public Class TextractAsyncProcessor
    Private ReadOnly _textractClient As AmazonTextractClient
    Private ReadOnly _s3Client As AmazonS3Client
    Private ReadOnly _bucketName As String
    Private ReadOnly _pollInterval As TimeSpan = TimeSpan.FromSeconds(5)
    Private ReadOnly _maxWaitTime As TimeSpan = TimeSpan.FromMinutes(10)

    Public Async Function ProcessDocumentAsync(localFilePath As String, Optional cancellationToken As CancellationToken = Nothing) As Task(Of DocumentResult)
        Dim s3Key = $"textract-uploads/{Guid.NewGuid()}{Path.GetExtension(localFilePath)}"

        Try
            ' Phase 1: Upload to S3
            Await UploadToS3Async(localFilePath, s3Key, cancellationToken)

            ' Phase 2: Start Textract job
            Dim jobId = Await StartTextractJobAsync(s3Key, cancellationToken)

            ' Phase 3: Poll until complete (up to 10 minutes)
            Dim pollResult = Await PollForCompletionAsync(jobId, cancellationToken)

            If Not pollResult.Success Then
                Throw New Exception($"Textract job failed: {pollResult.ErrorMessage}")
            End If

            ' Phase 4: Retrieve paginated results
            Return Await GetAllResultsAsync(jobId, cancellationToken)
        Finally
            ' Phase 5: S3 cleanup — must succeed or storage costs accumulate
            Await DeleteFromS3Async(s3Key, cancellationToken)
        End Try
    End Function

    Private Async Function PollForCompletionAsync(jobId As String, cancellationToken As CancellationToken) As Task(Of (Success As Boolean, ErrorMessage As String))
        Dim startTime = DateTime.UtcNow
        Dim pollCount As Integer = 0

        While DateTime.UtcNow - startTime < _maxWaitTime
            cancellationToken.ThrowIfCancellationRequested()

            Dim response = Await _textractClient.GetDocumentTextDetectionAsync(New GetDocumentTextDetectionRequest With {.JobId = jobId}, cancellationToken)

            pollCount += 1

            Select Case response.JobStatus
                Case JobStatus.SUCCEEDED
                    Return (True, Nothing)
                Case JobStatus.FAILED
                    Return (False, If(response.StatusMessage, "Unknown error"))
                Case JobStatus.IN_PROGRESS
                    Await Task.Delay(_pollInterval, cancellationToken)
                Case Else
                    Throw New Exception($"Unknown job status: {response.JobStatus}")
            End Select
        End While

        Return (False, "Job timed out")
    End Function
End Class

// IronOCR: same synchronous API regardless of document type or size
public string ProcessDocument(string filePath)
{
    using var input = new OcrInput();

    if (Path.GetExtension(filePath).Equals(".pdf", StringComparison.OrdinalIgnoreCase))
        input.LoadPdf(filePath);
    else
        input.LoadImage(filePath);

    return new IronTesseract().Read(input).Text;
}

Imports System.IO

' IronOCR: same synchronous API regardless of document type or size
Public Function ProcessDocument(filePath As String) As String
    Using input As New OcrInput()
        If Path.GetExtension(filePath).Equals(".pdf", StringComparison.OrdinalIgnoreCase) Then
            input.LoadPdf(filePath)
        Else
            input.LoadImage(filePath)
        End If

        Return New IronTesseract().Read(input).Text
    End Using
End Function

// Every environment needs these configured before this constructor succeeds
public TextractOcrService()
{
    // Reads credentials from environment, ~/.aws/credentials, or IAM role
    _client = new AmazonTextractClient(Amazon.RegionEndpoint.USEast1);
}

' Every environment needs these configured before this constructor succeeds
Public Sub New()
    ' Reads credentials from environment, ~/.aws/credentials, or IAM role
    _client = New AmazonTextractClient(Amazon.RegionEndpoint.USEast1)
End Sub

// One-time setup at application startup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Or from environment — recommended for deployments
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");

' One-time setup at application startup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

' Or from environment — recommended for deployments
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")

// Textract: filter flat block list by type
var lines = response.Blocks.Where(b => b.BlockType == BlockType.LINE);
var words = response.Blocks.Where(b => b.BlockType == BlockType.WORD);

// IronOCR: direct access to typed collections
var result = ocr.Read(imagePath);
var lines = result.Lines;   // IEnumerable<OcrResult.OcrResultLine>
var words = result.Words;   // IEnumerable<OcrResult.OcrResultWord>
foreach (var word in result.Words)
    Console.WriteLine($"'{word.Text}' at ({word.X},{word.Y}) confidence {word.Confidence}%");

' Textract: filter flat block list by type
Dim lines = response.Blocks.Where(Function(b) b.BlockType = BlockType.LINE)
Dim words = response.Blocks.Where(Function(b) b.BlockType = BlockType.WORD)

' IronOCR: direct access to typed collections
Dim result = ocr.Read(imagePath)
Dim lines = result.Lines   ' IEnumerable(Of OcrResult.OcrResultLine)
Dim words = result.Words   ' IEnumerable(Of OcrResult.OcrResultWord)
For Each word In result.Words
    Console.WriteLine($"'{word.Text}' at ({word.X},{word.Y}) confidence {word.Confidence}%")
Next

// Textract: upload to S3 → start job → poll → paginate → cleanup (50+ lines)
//IronOCRequivalent:
public string ProcessPdf(string pdfPath)
{
    var ocr = new IronTesseract();
    using var input = new OcrInput();
    input.LoadPdf(pdfPath);
    return ocr.Read(input).Text;
}

// Specific page ranges (no Textract equivalent without async job per range)
public string ProcessPdfPages(string pdfPath, int startPage, int endPage)
{
    var ocr = new IronTesseract();
    using var input = new OcrInput();
    input.LoadPdfPages(pdfPath, startPage, endPage);
    return ocr.Read(input).Text;
}

Imports IronOcr

Public Class OcrProcessor
    ' Textract: upload to S3 → start job → poll → paginate → cleanup (50+ lines)
    ' IronOCRequivalent:
    Public Function ProcessPdf(pdfPath As String) As String
        Dim ocr As New IronTesseract()
        Using input As New OcrInput()
            input.LoadPdf(pdfPath)
            Return ocr.Read(input).Text
        End Using
    End Function

    ' Specific page ranges (no Textract equivalent without async job per range)
    Public Function ProcessPdfPages(pdfPath As String, startPage As Integer, endPage As Integer) As String
        Dim ocr As New IronTesseract()
        Using input As New OcrInput()
            input.LoadPdfPages(pdfPath, startPage, endPage)
            Return ocr.Read(input).Text
        End Using
    End Function
End Class

// For documents that returned low-confidence results from Textract
using var input = new OcrInput();
input.LoadImage("low-quality-scan.jpg");

input.Deskew();              // Fix rotation from scanner misalignment
input.DeNoise();             // Remove scanner noise artifacts
input.Contrast();            // Boost faint text
input.EnhanceResolution(300); // Scale to optimal OCR resolution

var result = new IronTesseract().Read(input);
Console.WriteLine($"Confidence: {result.Confidence}%");

Imports IronOcr

Dim input As New OcrInput()
input.LoadImage("low-quality-scan.jpg")

input.Deskew()              ' Fix rotation from scanner misalignment
input.DeNoise()             ' Remove scanner noise artifacts
input.Contrast()            ' Boost faint text
input.EnhanceResolution(300) ' Scale to optimal OCR resolution

Dim result = New IronTesseract().Read(input)
Console.WriteLine($"Confidence: {result.Confidence}%")

// Preserves async call site for minimal refactoring
public async Task<string> ExtractTextAsync(string path)
{
    return await Task.Run(() => new IronTesseract().Read(path).Text);
}

Imports System.Threading.Tasks

' Preserves async call site for minimal refactoring
Public Async Function ExtractTextAsync(path As String) As Task(Of String)
    Return Await Task.Run(Function() New IronTesseract().Read(path).Text)
End Function